Metraipolis › archive › dc_a3866abd2bc2

ElasticFormer: Detecting Objects in HRW Shots via Elastic Computing Vision Transformer — arXiv:2610.39946

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39946
License (as archived)
CC0-1.0
Archived
2026-11-01T02:42:14.055Z
SHA-256 of the archived text
428f691617e5f83e1368e0c900ffb34ab0eec61b813fbec125955d2ae1e635a2
Stable URL of this page
https://metraipolis.com/documento/dc_a3866abd2bc2

How to cite

ElasticFormer: Detecting Objects in HRW Shots via Elastic Computing Vision Transformer — arXiv:2610.39946 — arXiv (en), https://arxiv.org/abs/2610.39946 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a3866abd2bc2 (Metraipolis archive dc_a3866abd2bc2, sha256 428f691617e5f83e1368e0c900ffb34ab0eec61b813fbec125955d2ae1e635a2)
BibTeX
@misc{dca3866abd2bc2,
  title = {ElasticFormer: Detecting Objects in HRW Shots via Elastic Computing Vision Transformer — arXiv:2610.39946},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39946},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a3866abd2bc2; sha256 428f691617e5f83e1368e0c900ffb34ab0eec61b813fbec125955d2ae1e635a2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39946. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in gigapixel-level imaging have brought High-Resolution Wide shots to the forefront of research. However, these images present significant challenges: extreme sparsity of foreground, gigapixel-level resolutions and diverse target counts. This makes traditional close-up detectors inaccurate and slow as they are overwhelmed by the background. Although previous research has explored sparse backbones, their fixed sparsity patterns lack the adaptability required to handle diverse target numbers. To address this, we introduce ElasticFormer, a sparse backbone that dynamically allocates computational resources based on foreground proportion. After scoring windows based on variance, proposed ElasticSelector module will predict the foreground proportion for top-k selection. The mechanism guides the model to select target-containing windows, scaling resources in areas where objects are clustered. We introduce a novel loss function combined with the 3-phase training strategy for ElasticSelector, allowing it to function properly when bounding box annotations are missing. A WSOD study is carried on PASCAL VOC 2007 to evaluate its extensibility. Further, ElasticNet is created to verify its backbone-agnostic nature. In experiments on the PANDA gigapixel benchmark, ElasticFormer reduces backbone FLOPs by 80% while achieving a significant improvement in AP50 when compared to fixed-ratio sparse methods.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.39946 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-01T02:16:43.961Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).